Abstract
Approximative measures of network sparsity in terms of norms tailored to dictionaries of computational units are investigated. Lower bounds on these norms of real-valued functions on finite domains are derived. The bounds are proven by combining the concentration of measure property of high-dimensional spaces with characterization of dictionaries of computational units in terms of their capacities and coherence measured by their covering numbers. The results are applied to dictionaries used in neurocomputing which have power-type covering numbers. Probabilistic results are illustrated by a concrete construction of a class of functions, computation of which by perceptron networks requires large number of units or it is unstable due to large output weights.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., LeCun, Y.: Scaling learning algorithms towards AI. In: Bottou, L., Chapelle, O., DeCoste, D., Weston, J. (eds.) Large-Scale Kernel Machines. MIT Press, Cambridge (2007)
Ba, L.J., Caruana, R.: Do deep networks really need to be deep? In: Ghahrani, Z., et al. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 1–9 (2014)
Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)
DeVore, R.A., Howard, R., Micchelli, C.: Optimal nonlinear approximation. Manuscripta Mathematica 63, 469–478 (1989)
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., Liao, Q.: Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review. Int. J. Autom. Comput. https://doi.org/10.1007/s11633-017-1054-2
Kainen, P.C., , V., Vogt, A.: Approximation by neural networks is not continuous. Neurocomputing 29, 47–56 (1999)
Kainen, P.C., , V., Vogt, A.: Geometry and topology of continuous best and near best approximations. J. Approx. Theor. 105, 252–262 (2000)
Kainen, P.C., , V., Vogt, A.: Continuity of approximation by neural networks in \({L}_p\)-spaces. Ann. Oper. Res. 101, 143–147 (2001)
Bengio, Y., Delalleau, O., Roux, N.L.: The curse of highly variable functions for local kernel machines. In: Advances in Neural Information Processing Systems, vol. 18, pp. 107–114. MIT Press, Cambridge (2006)
, V., Sanguineti, M.: Model complexities of shallow networks representing highly varying functions. Neurocomputing 171, 598–604 (2016)
Barron, A.R.: Neural net approximation. In: Narendra, K.S. (ed.) Proceedings of 7th Yale Workshop on Adaptive and Learning Systems, pp. 69–72. Yale University Press (1992)
, V.: Dimension-independent rates of approximation by neural networks. In: Warwick, K., Kárný, M. (eds.) Computer-Intensive Methods in Control and Signal Processing. The Curse of Dimensionality, pp. 261–270. Birkhäuser, Boston (1997)
, V.: Complexity estimates based on integral transforms induced by computational units. Neural Netw. 33, 160–167 (2012)
, V., Sanguineti, M.: Probabilistic lower bounds for approximation by shallow perceptron networks. Neural Netw. 91, 34–41 (2017)
, V.: Constructive lower bounds on model complexity of shallow perceptron networks. Neural Comput. Appl. 29, 305–315 (2018)
Fine, T.L.: Feedforward Neural Network Methodology. Springer, Heidelberg (1999). https://doi.org/10.1007/b97705
Plan, Y., Vershynin, R.: One-bit compressed sensing by linear programming. Commun. Pure Appl. Math. 66, 1275–1297 (2013)
Ito, Y.: Finite mapping by neural networks and truth functions. Math. Sci. 17, 69–77 (1992)
Kolmogorov, A.: Asymptotic characteristics of some completely bounded metric spaces. Dokl. Akad. Nauk. SSSR 108, 585–589 (1956)
Matoušek, J.: Lectures on Discrete Geometry. Springer, New York (2002). https://doi.org/10.1007/978-1-4613-0039-7
Schläfli, L.: Gesamelte Mathematische Abhandlungen, vol. 1. Birkhäuser, Basel (1950)
Makovoz, Y.: Random approximants and neural networks. J. Approx. Theor. 85, 98–109 (1996)
Haussler, D.: Sphere packing numbers for subsets of the Boolean n-cube with bounded Vapnik-Chervonenkis dimension. J. Comb. Theor. A 69(2), 217–232 (1995)
Kainen, P.C., , V.: Quasiorthogonal dimension of Euclidean spaces. Appl. Math. Lett. 6(3), 7–10 (1993)
Kainen, P.C., , V.: Quasiorthogonal dimension. In: Kosheleva, O., Shary, S., Xiang, G., Zapatrin, R. (eds.) Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy, etc. Methods and Their Applications. Springer (2018, to appear)
Tibshirani, R.: Regression shrinkage and selection via the Lasso. J. Roy. Stat. Soc. B 58, 267–288 (1996)
Acknowledgments
V.K. was partially supported by the Czech Grant Foundation grant GA18-23827S and institutional support of the Institute of Computer Science RVO 67985807.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Kůrková, V. (2018). Sparsity and Complexity of Networks Computing Highly-Varying Functions. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11141. Springer, Cham. https://doi.org/10.1007/978-3-030-01424-7_52
Download citation
DOI: https://doi.org/10.1007/978-3-030-01424-7_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01423-0
Online ISBN: 978-3-030-01424-7
eBook Packages: Computer ScienceComputer Science (R0)